File openssl-CVE-2016-0702-openssl101.patch of Package openssl1

From b3c1c872647cd3e15ea4eb951999eae3e69784ad Mon Sep 17 00:00:00 2001
From: Andy Polyakov <appro@openssl.org>
Date: Tue, 26 Jan 2016 11:34:41 +0100
Subject: [PATCH] bn/bn_exp.c: constant-time MOD_EXP_CTIME_COPY_FROM_PREBUF.

---
 crypto/bn/bn_exp.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 57 insertions(+), 18 deletions(-)

Index: openssl-1.0.1i/crypto/bn/bn_exp.c
===================================================================
--- openssl-1.0.1i.orig/crypto/bn/bn_exp.c	2016-02-24 21:03:57.686323833 +0100
+++ openssl-1.0.1i/crypto/bn/bn_exp.c	2016-02-24 21:04:02.282359896 +0100
@@ -111,6 +111,7 @@
 
 
 #include "cryptlib.h"
+#include "constant_time_locl.h"
 #include "bn_lcl.h"
 
 #include <stdlib.h>
@@ -534,30 +535,67 @@
  * as cache lines are concerned.  The following functions are used to transfer a BIGNUM
  * from/to that table. */
 
-static int MOD_EXP_CTIME_COPY_TO_PREBUF(const BIGNUM *b, int top, unsigned char *buf, int idx, int width)
+static int MOD_EXP_CTIME_COPY_TO_PREBUF(const BIGNUM *b, int top, unsigned char *buf, int idx, int window)
 	{
-	size_t i, j;
+	int i, j;
+    int width = 1 << window;
+    BN_ULONG *table = (BN_ULONG *)buf;
 
 	if (top > b->top)
 		top = b->top; /* this works because 'buf' is explicitly zeroed */
-	for (i = 0, j=idx; i < top * sizeof b->d[0]; i++, j+=width)
+	for (i = 0, j=idx; i < top; i++, j+=width)
 		{
-		buf[j] = ((unsigned char*)b->d)[i];
+		table[j] = b->d[i];
 		}
 
 	return 1;
 	}
 
-static int MOD_EXP_CTIME_COPY_FROM_PREBUF(BIGNUM *b, int top, unsigned char *buf, int idx, int width)
+static int MOD_EXP_CTIME_COPY_FROM_PREBUF(BIGNUM *b, int top, unsigned char *buf, int idx, int window)
 	{
-	size_t i, j;
+	int i, j;
+    int width = 1 << window;
+    volatile BN_ULONG *table = (volatile BN_ULONG *)buf;
 
 	if (bn_wexpand(b, top) == NULL)
 		return 0;
 
-	for (i=0, j=idx; i < top * sizeof b->d[0]; i++, j+=width)
-		{
-		((unsigned char*)b->d)[i] = buf[j];
+    if (window <= 3) {
+        for (i = 0; i < top; i++, table += width) {
+            BN_ULONG acc = 0;
+
+            for (j = 0; j < width; j++) {
+                acc |= table[j] &
+                       ((BN_ULONG)0 - (constant_time_eq_int(j,idx)&1));
+            }
+
+            b->d[i] = acc;
+        }
+    } else {
+        int xstride = 1 << (window - 2);
+        BN_ULONG y0, y1, y2, y3;
+
+        i = idx >> (window - 2);        /* equivalent of idx / xstride */
+        idx &= xstride - 1;             /* equivalent of idx % xstride */
+
+        y0 = (BN_ULONG)0 - (constant_time_eq_int(i,0)&1);
+        y1 = (BN_ULONG)0 - (constant_time_eq_int(i,1)&1);
+        y2 = (BN_ULONG)0 - (constant_time_eq_int(i,2)&1);
+        y3 = (BN_ULONG)0 - (constant_time_eq_int(i,3)&1);
+
+        for (i = 0; i < top; i++, table += width) {
+            BN_ULONG acc = 0;
+
+            for (j = 0; j < xstride; j++) {
+                acc |= ( (table[j + 0 * xstride] & y0) |
+                         (table[j + 1 * xstride] & y1) |
+                         (table[j + 2 * xstride] & y2) |
+                         (table[j + 3 * xstride] & y3) )
+                       & ((BN_ULONG)0 - (constant_time_eq_int(j,idx)&1));
+            }
+
+            b->d[i] = acc;
+        }
 		}
 
 	b->top = top;
@@ -767,8 +805,8 @@
     else
 #endif
 	{
-	if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 0, numPowers)) goto err;
-	if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&am,  top, powerbuf, 1, numPowers)) goto err;
+	if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 0, window)) goto err;
+	if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&am,  top, powerbuf, 1, window)) goto err;
 
 	/* If the window size is greater than 1, then calculate
 	 * val[i=2..2^winsize-1]. Powers are computed as a*a^(i-1)
@@ -778,20 +816,24 @@
 	if (window > 1)
 		{
 		if (!BN_mod_mul_montgomery(&tmp,&am,&am,mont,ctx))	goto err;
-		if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 2, numPowers)) goto err;
+		if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 2,
+                                              window)) goto err;
 		for (i=3; i<numPowers; i++)
 			{
 			/* Calculate a^i = a^(i-1) * a */
 			if (!BN_mod_mul_montgomery(&tmp,&am,&tmp,mont,ctx))
 				goto err;
-			if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, i, numPowers)) goto err;
+			if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, i,
+                                                  window)) goto err;
 			}
 		}
 
 	bits--;
-	for (wvalue=0, i=bits%window; i>=0; i--,bits--)
-		wvalue = (wvalue<<1)+BN_is_bit_set(p,bits);
-	if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&tmp,top,powerbuf,wvalue,numPowers)) goto err;
+        for (wvalue = 0, i = bits % window; i >= 0; i--, bits--)
+            wvalue = (wvalue << 1) + BN_is_bit_set(p, bits);
+        if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&tmp, top, powerbuf, wvalue,
+                                            window))
+            goto err;
  
 	/* Scan the exponent one window at a time starting from the most
 	 * significant bits.
@@ -808,7 +850,8 @@
   			}
  		
 		/* Fetch the appropriate pre-computed value from the pre-buf */
-		if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&am, top, powerbuf, wvalue, numPowers)) goto err;
+		if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&am, top, powerbuf, wvalue,
+                                                window)) goto err;
 
  		/* Multiply the result into the intermediate result */
  		if (!BN_mod_mul_montgomery(&tmp,&tmp,&am,mont,ctx)) goto err;
Index: openssl-1.0.1i/crypto/perlasm/x86_64-xlate.pl
===================================================================
--- openssl-1.0.1i.orig/crypto/perlasm/x86_64-xlate.pl	2016-02-24 21:03:57.686323833 +0100
+++ openssl-1.0.1i/crypto/perlasm/x86_64-xlate.pl	2016-02-24 21:04:02.282359896 +0100
@@ -121,7 +121,7 @@
 		$self->{sz} = "";
 	    } elsif ($self->{op} =~ /^v/) { # VEX
 		$self->{sz} = "";
-	    } elsif ($self->{op} =~ /movq/ && $line =~ /%xmm/) {
+	    } elsif ($self->{op} =~ /mov[dq]/ && $line =~ /%xmm/) {
 		$self->{sz} = "";
 	    } elsif ($self->{op} =~ /([a-z]{3,})([qlwb])$/) {
 		$self->{op} = $1;
Index: openssl-1.0.1i/crypto/bn/asm/x86_64-mont5.pl
===================================================================
--- openssl-1.0.1i.orig/crypto/bn/asm/x86_64-mont5.pl	2016-02-24 21:03:57.686323833 +0100
+++ openssl-1.0.1i/crypto/bn/asm/x86_64-mont5.pl	2016-02-24 21:04:02.282359896 +0100
@@ -66,60 +66,113 @@
 .align	16
 .Lmul_enter:
 	mov	${num}d,${num}d
-	mov	`($win64?56:8)`(%rsp),%r10d	# load 7th argument
+	movd	`($win64?56:8)`(%rsp),%xmm5	# load 7th argument
+	lea	.Linc(%rip),%r10
 	push	%rbx
 	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
 	push	%r15
-___
-$code.=<<___ if ($win64);
-	lea	-0x28(%rsp),%rsp
-	movaps	%xmm6,(%rsp)
-	movaps	%xmm7,0x10(%rsp)
+
 .Lmul_alloca:
-___
-$code.=<<___;
 	mov	%rsp,%rax
 	lea	2($num),%r11
 	neg	%r11
-	lea	(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+2))
+	lea	-264(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+2)+256+8)
 	and	\$-1024,%rsp		# minimize TLB usage
 
 	mov	%rax,8(%rsp,$num,8)	# tp[num+1]=%rsp
 .Lmul_body:
-	mov	$bp,%r12		# reassign $bp
+	lea	128($bp),%r12		# reassign $bp (+size optimization)
 ___
 		$bp="%r12";
 		$STRIDE=2**5*8;		# 5 is "window size"
 		$N=$STRIDE/4;		# should match cache line size
 $code.=<<___;
-	mov	%r10,%r11
-	shr	\$`log($N/8)/log(2)`,%r10
-	and	\$`$N/8-1`,%r11
-	not	%r10
-	lea	.Lmagic_masks(%rip),%rax
-	and	\$`2**5/($N/8)-1`,%r10	# 5 is "window size"
-	lea	96($bp,%r11,8),$bp	# pointer within 1st cache line
-	movq	0(%rax,%r10,8),%xmm4	# set of masks denoting which
-	movq	8(%rax,%r10,8),%xmm5	# cache line contains element
-	movq	16(%rax,%r10,8),%xmm6	# denoted by 7th argument
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	movdqa	0(%r10),%xmm0		# 00000001000000010000000000000000
+	movdqa	16(%r10),%xmm1		# 00000002000000020000000200000002
+	lea	24-112(%rsp,$num,8),%r10# place the mask after tp[num+3] (+ICache optimization)
+	and	\$-16,%r10
+
+	pshufd	\$0,%xmm5,%xmm5		# broadcast index
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..31 to index and save result to stack
+#
+$code.=<<___;
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0		# compare to 1,0
+	.byte	0x67
+	movdqa	%xmm4,%xmm3
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1		# compare to 3,2
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2		# compare to 5,4
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3		# compare to 7,6
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	movdqa	%xmm4,%xmm3
+___
+}
+$code.=<<___;				# last iteration can be optimized
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+
+	paddd	%xmm2,%xmm3
+	.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	pand	`16*($k+0)-128`($bp),%xmm0	# while it's still in register
+
+	pand	`16*($k+1)-128`($bp),%xmm1
+	pand	`16*($k+2)-128`($bp),%xmm2
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	pand	`16*($k+3)-128`($bp),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm4
+	movdqa	`16*($k+1)-128`($bp),%xmm5
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	pand	`16*($k+0)+112`(%r10),%xmm4
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+1)+112`(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	`16*($k+2)+112`(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	`16*($k+3)+112`(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+}
+$code.=<<___;
+	por	%xmm1,%xmm0
+	pshufd	\$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	movq	%xmm0,$m0		# m0=bp[0]
 
 	mov	($n0),$n0		# pull n0[0] value
@@ -128,29 +181,14 @@
 	xor	$i,$i			# i=0
 	xor	$j,$j			# j=0
 
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-
 	mov	$n0,$m1
 	mulq	$m0			# ap[0]*bp[0]
 	mov	%rax,$lo0
 	mov	($np),%rax
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$lo0,$m1		# "tp[0]"*n0
 	mov	%rdx,$hi0
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$lo0		# discarded
 	mov	8($ap),%rax
@@ -183,8 +221,6 @@
 	cmp	$num,$j
 	jne	.L1st
 
-	movq	%xmm0,$m0		# bp[1]
-
 	add	%rax,$hi1
 	mov	($ap),%rax		# ap[0]
 	adc	\$0,%rdx
@@ -204,33 +240,46 @@
 	jmp	.Louter
 .align	16
 .Louter:
+	lea	24+128(%rsp,$num,8),%rdx	# where 256-byte mask is (+size optimization)
+	and	\$-16,%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+___
+for($k=0;$k<$STRIDE/16;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm0
+	movdqa	`16*($k+1)-128`($bp),%xmm1
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+0)-128`(%rdx),%xmm0
+	pand	`16*($k+1)-128`(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	`16*($k+2)-128`(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	`16*($k+3)-128`(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+___
+}
+$code.=<<___;
+	por	%xmm5,%xmm4
+	pshufd	\$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	lea	$STRIDE($bp),$bp
+	movq	%xmm0,$m0		# m0=bp[i]
+
 	xor	$j,$j			# j=0
 	mov	$n0,$m1
 	mov	(%rsp),$lo0
 
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-
 	mulq	$m0			# ap[0]*bp[i]
 	add	%rax,$lo0		# ap[0]*bp[i]+tp[0]
 	mov	($np),%rax
 	adc	\$0,%rdx
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$lo0,$m1		# tp[0]*n0
 	mov	%rdx,$hi0
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$lo0		# discarded
 	mov	8($ap),%rax
@@ -266,8 +315,6 @@
 	cmp	$num,$j
 	jne	.Linner
 
-	movq	%xmm0,$m0		# bp[i+1]
-
 	add	%rax,$hi1
 	mov	($ap),%rax		# ap[0]
 	adc	\$0,%rdx
@@ -321,13 +368,7 @@
 
 	mov	8(%rsp,$num,8),%rsi	# restore %rsp
 	mov	\$1,%rax
-___
-$code.=<<___ if ($win64);
-	movaps	(%rsi),%xmm6
-	movaps	0x10(%rsi),%xmm7
-	lea	0x28(%rsi),%rsi
-___
-$code.=<<___;
+
 	mov	(%rsi),%r15
 	mov	8(%rsi),%r14
 	mov	16(%rsi),%r13
@@ -348,91 +389,130 @@
 bn_mul4x_mont_gather5:
 .Lmul4x_enter:
 	mov	${num}d,${num}d
-	mov	`($win64?56:8)`(%rsp),%r10d	# load 7th argument
+	movd	`($win64?56:8)`(%rsp),%xmm5	# load 7th argument
+	lea	.Linc(%rip),%r10
 	push	%rbx
 	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
 	push	%r15
-___
-$code.=<<___ if ($win64);
-	lea	-0x28(%rsp),%rsp
-	movaps	%xmm6,(%rsp)
-	movaps	%xmm7,0x10(%rsp)
+
 .Lmul4x_alloca:
-___
-$code.=<<___;
 	mov	%rsp,%rax
 	lea	4($num),%r11
 	neg	%r11
-	lea	(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+4))
+	lea	-256(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+4)+256)
 	and	\$-1024,%rsp		# minimize TLB usage
 
 	mov	%rax,8(%rsp,$num,8)	# tp[num+1]=%rsp
 .Lmul4x_body:
 	mov	$rp,16(%rsp,$num,8)	# tp[num+2]=$rp
-	mov	%rdx,%r12		# reassign $bp
+	lea	128(%rdx),%r12		# reassign $bp (+size optimization)
 ___
 		$bp="%r12";
 		$STRIDE=2**5*8;		# 5 is "window size"
 		$N=$STRIDE/4;		# should match cache line size
 $code.=<<___;
-	mov	%r10,%r11
-	shr	\$`log($N/8)/log(2)`,%r10
-	and	\$`$N/8-1`,%r11
-	not	%r10
-	lea	.Lmagic_masks(%rip),%rax
-	and	\$`2**5/($N/8)-1`,%r10	# 5 is "window size"
-	lea	96($bp,%r11,8),$bp	# pointer within 1st cache line
-	movq	0(%rax,%r10,8),%xmm4	# set of masks denoting which
-	movq	8(%rax,%r10,8),%xmm5	# cache line contains element
-	movq	16(%rax,%r10,8),%xmm6	# denoted by 7th argument
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	movdqa	0(%r10),%xmm0		# 00000001000000010000000000000000
+	movdqa	16(%r10),%xmm1		# 00000002000000020000000200000002
+	lea	32-112(%rsp,$num,8),%r10# place the mask after tp[num+4] (+ICache optimization)
+
+	pshufd	\$0,%xmm5,%xmm5		# broadcast index
+	movdqa	%xmm1,%xmm4
+	.byte	0x67,0x67
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..31 to index and save result to stack
+#
+$code.=<<___;
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0		# compare to 1,0
+	.byte	0x67
+	movdqa	%xmm4,%xmm3
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1		# compare to 3,2
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2		# compare to 5,4
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3		# compare to 7,6
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	movdqa	%xmm4,%xmm3
+___
+}
+$code.=<<___;				# last iteration can be optimized
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+
+	paddd	%xmm2,%xmm3
+	.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	pand	`16*($k+0)-128`($bp),%xmm0	# while it's still in register
+
+	pand	`16*($k+1)-128`($bp),%xmm1
+	pand	`16*($k+2)-128`($bp),%xmm2
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	pand	`16*($k+3)-128`($bp),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm4
+	movdqa	`16*($k+1)-128`($bp),%xmm5
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	pand	`16*($k+0)+112`(%r10),%xmm4
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+1)+112`(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	`16*($k+2)+112`(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	`16*($k+3)+112`(%r10),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+}
+$code.=<<___;
+	por	%xmm1,%xmm0
+	pshufd	\$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	movq	%xmm0,$m0		# m0=bp[0]
+
 	mov	($n0),$n0		# pull n0[0] value
 	mov	($ap),%rax
 
 	xor	$i,$i			# i=0
 	xor	$j,$j			# j=0
 
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-
 	mov	$n0,$m1
 	mulq	$m0			# ap[0]*bp[0]
 	mov	%rax,$A[0]
 	mov	($np),%rax
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$A[0],$m1		# "tp[0]"*n0
 	mov	%rdx,$A[1]
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$A[0]		# discarded
 	mov	8($ap),%rax
@@ -550,8 +630,6 @@
 	mov	$N[1],-16(%rsp,$j,8)	# tp[j-1]
 	mov	%rdx,$N[0]
 
-	movq	%xmm0,$m0		# bp[1]
-
 	xor	$N[1],$N[1]
 	add	$A[0],$N[0]
 	adc	\$0,$N[1]
@@ -561,12 +639,34 @@
 	lea	1($i),$i		# i++
 .align	4
 .Louter4x:
+	lea	32+128(%rsp,$num,8),%rdx	# where 256-byte mask is (+size optimization)
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+___
+for($k=0;$k<$STRIDE/16;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm0
+	movdqa	`16*($k+1)-128`($bp),%xmm1
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+0)-128`(%rdx),%xmm0
+	pand	`16*($k+1)-128`(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	`16*($k+2)-128`(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	`16*($k+3)-128`(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+___
+}
+$code.=<<___;
+	por	%xmm5,%xmm4
+	pshufd	\$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	lea	$STRIDE($bp),$bp
+	movq	%xmm0,$m0		# m0=bp[i]
+
 	xor	$j,$j			# j=0
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
 
 	mov	(%rsp),$A[0]
 	mov	$n0,$m1
@@ -575,18 +675,9 @@
 	mov	($np),%rax
 	adc	\$0,%rdx
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$A[0],$m1		# tp[0]*n0
 	mov	%rdx,$A[1]
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$A[0]		# "$N[0]", discarded
 	mov	8($ap),%rax
@@ -718,7 +809,6 @@
 	mov	$N[0],-24(%rsp,$j,8)	# tp[j-1]
 	mov	%rdx,$N[0]
 
-	movq	%xmm0,$m0		# bp[i+1]
 	mov	$N[1],-16(%rsp,$j,8)	# tp[j-1]
 
 	xor	$N[1],$N[1]
@@ -809,13 +899,7 @@
 $code.=<<___;
 	mov	8(%rsp,$num,8),%rsi	# restore %rsp
 	mov	\$1,%rax
-___
-$code.=<<___ if ($win64);
-	movaps	(%rsi),%xmm6
-	movaps	0x10(%rsi),%xmm7
-	lea	0x28(%rsi),%rsi
-___
-$code.=<<___;
+
 	mov	(%rsi),%r15
 	mov	8(%rsi),%r14
 	mov	16(%rsi),%r13
@@ -830,8 +914,8 @@
 }}}
 
 {
-my ($inp,$num,$tbl,$idx)=$win64?("%rcx","%rdx","%r8", "%r9") : # Win64 order
-				("%rdi","%rsi","%rdx","%rcx"); # Unix order
+my ($inp,$num,$tbl,$idx)=$win64?("%rcx","%rdx","%r8", "%r9d") : # Win64 order
+				("%rdi","%rsi","%rdx","%ecx"); # Unix order
 my $out=$inp;
 my $STRIDE=2**5*8;
 my $N=$STRIDE/4;
@@ -859,53 +943,89 @@
 .type	bn_gather5,\@abi-omnipotent
 .align	16
 bn_gather5:
-___
-$code.=<<___ if ($win64);
-.LSEH_begin_bn_gather5:
+.LSEH_begin_bn_gather5:			# Win64 thing, but harmless in other cases
 	# I can't trust assembler to use specific encoding:-(
-	.byte	0x48,0x83,0xec,0x28		#sub	\$0x28,%rsp
-	.byte	0x0f,0x29,0x34,0x24		#movaps	%xmm6,(%rsp)
-	.byte	0x0f,0x29,0x7c,0x24,0x10	#movdqa	%xmm7,0x10(%rsp)
-___
-$code.=<<___;
-	mov	$idx,%r11
-	shr	\$`log($N/8)/log(2)`,$idx
-	and	\$`$N/8-1`,%r11
-	not	$idx
-	lea	.Lmagic_masks(%rip),%rax
-	and	\$`2**5/($N/8)-1`,$idx	# 5 is "window size"
-	lea	96($tbl,%r11,8),$tbl	# pointer within 1st cache line
-	movq	0(%rax,$idx,8),%xmm4	# set of masks denoting which
-	movq	8(%rax,$idx,8),%xmm5	# cache line contains element
-	movq	16(%rax,$idx,8),%xmm6	# denoted by 7th argument
-	movq	24(%rax,$idx,8),%xmm7
+	.byte	0x4c,0x8d,0x14,0x24			# lea    (%rsp),%r10
+	.byte	0x48,0x81,0xec,0x08,0x01,0x00,0x00	# sub	$0x108,%rsp
+	lea	.Linc(%rip),%rax
+	and	\$-16,%rsp		# shouldn't be formally required
+
+	movd	$idx,%xmm5
+	movdqa	0(%rax),%xmm0		# 00000001000000010000000000000000
+	movdqa	16(%rax),%xmm1		# 00000002000000020000000200000002
+	lea	128($tbl),%r11		# size optimization
+	lea	128(%rsp),%rax		# size optimization
+
+	pshufd	\$0,%xmm5,%xmm5		# broadcast $idx
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..31 to $idx and save result to stack
+#
+for($i=0;$i<$STRIDE/16;$i+=4) {
+$code.=<<___;
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0		# compare to 1,0
+___
+$code.=<<___	if ($i);
+	movdqa	%xmm3,`16*($i-1)-128`(%rax)
+___
+$code.=<<___;
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1		# compare to 3,2
+	movdqa	%xmm0,`16*($i+0)-128`(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2		# compare to 5,4
+	movdqa	%xmm1,`16*($i+1)-128`(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3		# compare to 7,6
+	movdqa	%xmm2,`16*($i+2)-128`(%rax)
+	movdqa	%xmm4,%xmm2
+___
+}
+$code.=<<___;
+	movdqa	%xmm3,`16*($i-1)-128`(%rax)
 	jmp	.Lgather
-.align	16
-.Lgather:
-	movq	`0*$STRIDE/4-96`($tbl),%xmm0
-	movq	`1*$STRIDE/4-96`($tbl),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($tbl),%xmm2
-	pand	%xmm5,%xmm1
-	movq	`3*$STRIDE/4-96`($tbl),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-	por	%xmm2,%xmm0
-	lea	$STRIDE($tbl),$tbl
-	por	%xmm3,%xmm0
 
+.align	32
+.Lgather:
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+___
+for($i=0;$i<$STRIDE/16;$i+=4) {
+$code.=<<___;
+	movdqa	`16*($i+0)-128`(%r11),%xmm0
+	movdqa	`16*($i+1)-128`(%r11),%xmm1
+	movdqa	`16*($i+2)-128`(%r11),%xmm2
+	pand	`16*($i+0)-128`(%rax),%xmm0
+	movdqa	`16*($i+3)-128`(%r11),%xmm3
+	pand	`16*($i+1)-128`(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	`16*($i+2)-128`(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	`16*($i+3)-128`(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+___
+}
+$code.=<<___;
+	por	%xmm5,%xmm4
+	lea	$STRIDE(%r11),%r11
+	pshufd	\$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
 	movq	%xmm0,($out)		# m0=bp[0]
 	lea	8($out),$out
 	sub	\$1,$num
 	jnz	.Lgather
-___
-$code.=<<___ if ($win64);
-	movaps	(%rsp),%xmm6
-	movaps	0x10(%rsp),%xmm7
-	lea	0x28(%rsp),%rsp
-___
-$code.=<<___;
+
+	lea	(%r10),%rsp
 	ret
 .LSEH_end_bn_gather5:
 .size	bn_gather5,.-bn_gather5
@@ -913,9 +1033,9 @@
 }
 $code.=<<___;
 .align	64
-.Lmagic_masks:
-	.long	0,0, 0,0, 0,0, -1,-1
-	.long	0,0, 0,0, 0,0,  0,0
+.Linc:
+	.long	0,0, 1,1
+	.long	2,2, 2,2
 .asciz	"Montgomery Multiplication with scatter/gather for x86_64, CRYPTOGAMS by <appro\@openssl.org>"
 ___
 
@@ -954,7 +1074,7 @@
 	cmp	%r10,%rbx		# context->Rip<end of prologue label
 	jb	.Lcommon_seh_tail
 
-	lea	`40+48`(%rax),%rax
+	lea	48(%rax),%rax
 
 	mov	4(%r11),%r10d		# HandlerData[1]
 	lea	(%rsi,%r10),%r10	# end of alloca label
@@ -971,9 +1091,7 @@
 	mov	192($context),%r10	# pull $num
 	mov	8(%rax,%r10,8),%rax	# pull saved stack pointer
 
-	movaps	(%rax),%xmm0
-	movaps	16(%rax),%xmm1
-	lea	`40+48`(%rax),%rax
+	lea	48(%rax),%rax
 
 	mov	-8(%rax),%rbx
 	mov	-16(%rax),%rbp
@@ -987,8 +1105,6 @@
 	mov	%r13,224($context)	# restore context->R13
 	mov	%r14,232($context)	# restore context->R14
 	mov	%r15,240($context)	# restore context->R15
-	movups	%xmm0,512($context)	# restore context->Xmm6
-	movups	%xmm1,528($context)	# restore context->Xmm7
 
 .Lcommon_seh_tail:
 	mov	8(%rax),%rdi
@@ -1057,10 +1173,9 @@
 	.rva	.Lmul4x_alloca,.Lmul4x_body,.Lmul4x_epilogue	# HandlerData[]
 .align	8
 .LSEH_info_bn_gather5:
-        .byte   0x01,0x0d,0x05,0x00
-        .byte   0x0d,0x78,0x01,0x00	#movaps	0x10(rsp),xmm7
-        .byte   0x08,0x68,0x00,0x00	#movaps	(rsp),xmm6
-        .byte   0x04,0x42,0x00,0x00	#sub	rsp,0x28
+	.byte	0x01,0x0b,0x03,0x0a
+	.byte	0x0b,0x01,0x21,0x00	# sub	rsp,0x108
+	.byte	0x04,0xa3,0x00,0x00	# lea	r10,(rsp), set_frame r10
 .align	8
 ___
 }
Index: openssl-1.0.1i/crypto/constant_time_locl.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ openssl-1.0.1i/crypto/constant_time_locl.h	2016-02-24 21:05:06.674870669 +0100
@@ -0,0 +1,211 @@
+/* crypto/constant_time_locl.h */
+/*-
+ * Utilities for constant-time cryptography.
+ *
+ * Author: Emilia Kasper (emilia@openssl.org)
+ * Based on previous work by Bodo Moeller, Emilia Kasper, Adam Langley
+ * (Google).
+ * ====================================================================
+ * Copyright (c) 2014 The OpenSSL Project.  All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ *
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
+#ifndef HEADER_CONSTANT_TIME_LOCL_H
+# define HEADER_CONSTANT_TIME_LOCL_H
+
+# include "e_os.h"              /* For 'inline' */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*-
+ * The boolean methods return a bitmask of all ones (0xff...f) for true
+ * and 0 for false. This is useful for choosing a value based on the result
+ * of a conditional in constant time. For example,
+ *
+ * if (a < b) {
+ *   c = a;
+ * } else {
+ *   c = b;
+ * }
+ *
+ * can be written as
+ *
+ * unsigned int lt = constant_time_lt(a, b);
+ * c = constant_time_select(lt, a, b);
+ */
+
+/*
+ * Returns the given value with the MSB copied to all the other
+ * bits. Uses the fact that arithmetic shift shifts-in the sign bit.
+ * However, this is not ensured by the C standard so you may need to
+ * replace this with something else on odd CPUs.
+ */
+static inline unsigned int constant_time_msb(unsigned int a);
+
+/*
+ * Returns 0xff..f if a < b and 0 otherwise.
+ */
+static inline unsigned int constant_time_lt(unsigned int a, unsigned int b);
+/* Convenience method for getting an 8-bit mask. */
+static inline unsigned char constant_time_lt_8(unsigned int a,
+                                               unsigned int b);
+
+/*
+ * Returns 0xff..f if a >= b and 0 otherwise.
+ */
+static inline unsigned int constant_time_ge(unsigned int a, unsigned int b);
+/* Convenience method for getting an 8-bit mask. */
+static inline unsigned char constant_time_ge_8(unsigned int a,
+                                               unsigned int b);
+
+/*
+ * Returns 0xff..f if a == 0 and 0 otherwise.
+ */
+static inline unsigned int constant_time_is_zero(unsigned int a);
+/* Convenience method for getting an 8-bit mask. */
+static inline unsigned char constant_time_is_zero_8(unsigned int a);
+
+/*
+ * Returns 0xff..f if a == b and 0 otherwise.
+ */
+static inline unsigned int constant_time_eq(unsigned int a, unsigned int b);
+/* Convenience method for getting an 8-bit mask. */
+static inline unsigned char constant_time_eq_8(unsigned int a,
+                                               unsigned int b);
+/* Signed integers. */
+static inline unsigned int constant_time_eq_int(int a, int b);
+/* Convenience method for getting an 8-bit mask. */
+static inline unsigned char constant_time_eq_int_8(int a, int b);
+
+/*-
+ * Returns (mask & a) | (~mask & b).
+ *
+ * When |mask| is all 1s or all 0s (as returned by the methods above),
+ * the select methods return either |a| (if |mask| is nonzero) or |b|
+ * (if |mask| is zero).
+ */
+static inline unsigned int constant_time_select(unsigned int mask,
+                                                unsigned int a,
+                                                unsigned int b);
+/* Convenience method for unsigned chars. */
+static inline unsigned char constant_time_select_8(unsigned char mask,
+                                                   unsigned char a,
+                                                   unsigned char b);
+/* Convenience method for signed integers. */
+static inline int constant_time_select_int(unsigned int mask, int a, int b);
+
+static inline unsigned int constant_time_msb(unsigned int a)
+{
+    return 0 - (a >> (sizeof(a) * 8 - 1));
+}
+
+static inline unsigned int constant_time_lt(unsigned int a, unsigned int b)
+{
+    return constant_time_msb(a ^ ((a ^ b) | ((a - b) ^ b)));
+}
+
+static inline unsigned char constant_time_lt_8(unsigned int a, unsigned int b)
+{
+    return (unsigned char)(constant_time_lt(a, b));
+}
+
+static inline unsigned int constant_time_ge(unsigned int a, unsigned int b)
+{
+    return ~constant_time_lt(a, b);
+}
+
+static inline unsigned char constant_time_ge_8(unsigned int a, unsigned int b)
+{
+    return (unsigned char)(constant_time_ge(a, b));
+}
+
+static inline unsigned int constant_time_is_zero(unsigned int a)
+{
+    return constant_time_msb(~a & (a - 1));
+}
+
+static inline unsigned char constant_time_is_zero_8(unsigned int a)
+{
+    return (unsigned char)(constant_time_is_zero(a));
+}
+
+static inline unsigned int constant_time_eq(unsigned int a, unsigned int b)
+{
+    return constant_time_is_zero(a ^ b);
+}
+
+static inline unsigned char constant_time_eq_8(unsigned int a, unsigned int b)
+{
+    return (unsigned char)(constant_time_eq(a, b));
+}
+
+static inline unsigned int constant_time_eq_int(int a, int b)
+{
+    return constant_time_eq((unsigned)(a), (unsigned)(b));
+}
+
+static inline unsigned char constant_time_eq_int_8(int a, int b)
+{
+    return constant_time_eq_8((unsigned)(a), (unsigned)(b));
+}
+
+static inline unsigned int constant_time_select(unsigned int mask,
+                                                unsigned int a,
+                                                unsigned int b)
+{
+    return (mask & a) | (~mask & b);
+}
+
+static inline unsigned char constant_time_select_8(unsigned char mask,
+                                                   unsigned char a,
+                                                   unsigned char b)
+{
+    return (unsigned char)(constant_time_select(mask, a, b));
+}
+
+static inline int constant_time_select_int(unsigned int mask, int a, int b)
+{
+    return (int)(constant_time_select(mask, (unsigned)(a), (unsigned)(b)));
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif                          /* HEADER_CONSTANT_TIME_LOCL_H */